Russell P. Bobbitt - Pleasantville NY, US Quanfu Fan - Somerville MA, US Jiyan Pan - Pittsburgh PA, US Sharathchandra U. Pankanti - Darien CT, US
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY
International Classification:
G06K 9/00
US Classification:
382103
Abstract:
A foreground object blob having a bounding box detected in frame image data is classified by a finite state machine as a background, moving foreground, or temporally static object, namely as the temporally static object when the detected bounding box is distinguished from a background model of a scene image of the video data input and remains static in the scene image for a threshold period. The bounding box is tracked through matching masks in subsequent frame data of the video data input, and the object sub-classified within a visible sub-state, an occluded sub-state, or another sub-state that is not visible and not occluded as a function of a static value ratio. The ratio is a number of pixels determined to be static by tracking in a foreground region of the background model corresponding to the tracked object bounding box over a total number of pixels of the foreground region.
Quanfu Fan - Somerville MA, US Prasad Gabbur - Sleepy Hollow NY, US Sachiko Miyazawa - Bronx NY, US Jiyan Pan - Pittsburgh PA, US Sharathchandra U. Pankanti - Darien CT, US Hoang Trinh - Mt. Vernon NY, US
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY
International Classification:
G06K 9/62
US Classification:
382159
Abstract:
Events are classified through string pattern recognition. Text labels are assigned to image primitives in a time-ordered set of training images and to related time-ordered transactions in an associated training transaction log in a combined time-ordered training string of text labels as a function of image types. Transactions are labeled in a training transaction log with a transaction label, a training primitive image of a start of a transaction with a start image text label, a training primitive of an entry of a transaction into the log with an entry image text label, and a training primitive of a conclusion of a transaction with an ending image text label. Positive subset string patterns are discovered representing true events from the combined time-ordered training string of text labels, and negative subset string patterns defined by removing single transaction primitive labels from the positive subset string patterns.
Carnegie Mellon University since Aug 2008
Research Assistant
Microsoft Corporation Jun 2011 - Aug 2011
Research Intern
IBM Watson Research May 2010 - Dec 2010
Research Intern
Intel Research Pittsburgh Jun 2009 - Aug 2009
Research Intern
IBM Jul 2007 - Jun 2008
Software Engineer Intern
Education:
Carnegie Mellon University 2008 - 2014
Ph.D., Artificial Intelligence and Robotics
Carnegie Mellon University 2008 - 2010
M.S., Artificial Intelligence and Robotics
Fudan University 2005 - 2008
M.S., Electronic Engineering
Fudan University 2001 - 2005
B.S., Electronic Engineering
Skills:
Information Retrieval R Algorithms C Matlab Image Processing Natural Language Processing Signal Processing Artificial Intelligence Latex Opencv Watson Mathematical Modeling Fpga C++ Computer Vision Python Robotics Simulations Optimization Research Computer Science Machine Learning Data Mining Pattern Recognition
Interests:
Wushu Western Classical Music Table Tennis Angling Cycling Piano Singing
Jiyan Pan's Public Profile on Plaxo. Plaxo helps members like Jiyan Pan keep in touch with the people who really matter, helping them to connect, keep each other's contact data up ...